| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 27270, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18335166850018336, | |
| "grad_norm": 2.6387195587158203, | |
| "learning_rate": 4.908324165749908e-05, | |
| "loss": 2.1955, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3667033370003667, | |
| "grad_norm": 2.266592025756836, | |
| "learning_rate": 4.816648331499817e-05, | |
| "loss": 2.0932, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5500550055005501, | |
| "grad_norm": 3.0838563442230225, | |
| "learning_rate": 4.724972497249725e-05, | |
| "loss": 2.048, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7334066740007334, | |
| "grad_norm": 2.5882773399353027, | |
| "learning_rate": 4.633296662999633e-05, | |
| "loss": 2.0419, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9167583425009168, | |
| "grad_norm": 2.441417694091797, | |
| "learning_rate": 4.541620828749542e-05, | |
| "loss": 2.0299, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.1001100110011002, | |
| "grad_norm": 2.2205169200897217, | |
| "learning_rate": 4.449944994499451e-05, | |
| "loss": 1.9854, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.2834616795012834, | |
| "grad_norm": 2.802492380142212, | |
| "learning_rate": 4.358269160249359e-05, | |
| "loss": 1.9621, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.466813348001467, | |
| "grad_norm": 6.791469573974609, | |
| "learning_rate": 4.266593325999267e-05, | |
| "loss": 1.957, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.6501650165016502, | |
| "grad_norm": 2.5560526847839355, | |
| "learning_rate": 4.174917491749175e-05, | |
| "loss": 1.9447, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.8335166850018334, | |
| "grad_norm": 2.623948812484741, | |
| "learning_rate": 4.0832416574990836e-05, | |
| "loss": 1.9517, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.0168683535020167, | |
| "grad_norm": 2.395932674407959, | |
| "learning_rate": 3.991565823248992e-05, | |
| "loss": 1.9559, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.2002200220022003, | |
| "grad_norm": 2.153954267501831, | |
| "learning_rate": 3.8998899889989e-05, | |
| "loss": 1.9099, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.3835716905023836, | |
| "grad_norm": 2.0535569190979004, | |
| "learning_rate": 3.808214154748808e-05, | |
| "loss": 1.8994, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.566923359002567, | |
| "grad_norm": 2.264138698577881, | |
| "learning_rate": 3.716538320498717e-05, | |
| "loss": 1.9069, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.7502750275027505, | |
| "grad_norm": 1.9639852046966553, | |
| "learning_rate": 3.624862486248625e-05, | |
| "loss": 1.9109, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.933626696002934, | |
| "grad_norm": 1.975576639175415, | |
| "learning_rate": 3.5331866519985334e-05, | |
| "loss": 1.9207, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.116978364503117, | |
| "grad_norm": 1.8623844385147095, | |
| "learning_rate": 3.4415108177484414e-05, | |
| "loss": 1.8771, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.3003300330033003, | |
| "grad_norm": 2.512981653213501, | |
| "learning_rate": 3.34983498349835e-05, | |
| "loss": 1.8801, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.4836817015034836, | |
| "grad_norm": 2.324370861053467, | |
| "learning_rate": 3.258159149248258e-05, | |
| "loss": 1.8746, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.667033370003667, | |
| "grad_norm": 2.3853843212127686, | |
| "learning_rate": 3.166483314998166e-05, | |
| "loss": 1.8549, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.8503850385038505, | |
| "grad_norm": 1.7555441856384277, | |
| "learning_rate": 3.074807480748075e-05, | |
| "loss": 1.8724, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 4.033736707004033, | |
| "grad_norm": 2.166177749633789, | |
| "learning_rate": 2.983131646497983e-05, | |
| "loss": 1.8574, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 4.2170883755042174, | |
| "grad_norm": 2.927156925201416, | |
| "learning_rate": 2.891455812247892e-05, | |
| "loss": 1.8507, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.400440044004401, | |
| "grad_norm": 2.2842493057250977, | |
| "learning_rate": 2.7997799779978003e-05, | |
| "loss": 1.8447, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 4.583791712504584, | |
| "grad_norm": 2.1565608978271484, | |
| "learning_rate": 2.7081041437477084e-05, | |
| "loss": 1.8359, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.767143381004767, | |
| "grad_norm": 2.3850159645080566, | |
| "learning_rate": 2.6164283094976168e-05, | |
| "loss": 1.8413, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.9504950495049505, | |
| "grad_norm": 2.2318992614746094, | |
| "learning_rate": 2.5247524752475248e-05, | |
| "loss": 1.8397, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 5.133846718005134, | |
| "grad_norm": 2.347505569458008, | |
| "learning_rate": 2.4330766409974332e-05, | |
| "loss": 1.8196, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 5.317198386505317, | |
| "grad_norm": 2.1487085819244385, | |
| "learning_rate": 2.3414008067473413e-05, | |
| "loss": 1.8309, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 5.5005500550055, | |
| "grad_norm": 2.21701717376709, | |
| "learning_rate": 2.24972497249725e-05, | |
| "loss": 1.8212, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 5.683901723505684, | |
| "grad_norm": 2.2371625900268555, | |
| "learning_rate": 2.158049138247158e-05, | |
| "loss": 1.8148, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 5.867253392005868, | |
| "grad_norm": 2.157254457473755, | |
| "learning_rate": 2.0663733039970665e-05, | |
| "loss": 1.83, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 6.050605060506051, | |
| "grad_norm": 2.467193603515625, | |
| "learning_rate": 1.9746974697469746e-05, | |
| "loss": 1.8115, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 6.233956729006234, | |
| "grad_norm": 2.3348140716552734, | |
| "learning_rate": 1.883021635496883e-05, | |
| "loss": 1.8037, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 6.417308397506417, | |
| "grad_norm": 2.6734750270843506, | |
| "learning_rate": 1.7913458012467914e-05, | |
| "loss": 1.805, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 6.600660066006601, | |
| "grad_norm": 2.0465357303619385, | |
| "learning_rate": 1.6996699669966998e-05, | |
| "loss": 1.8014, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 6.784011734506784, | |
| "grad_norm": 2.7078983783721924, | |
| "learning_rate": 1.6079941327466082e-05, | |
| "loss": 1.7988, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 6.967363403006967, | |
| "grad_norm": 2.771340847015381, | |
| "learning_rate": 1.5163182984965163e-05, | |
| "loss": 1.796, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 7.15071507150715, | |
| "grad_norm": 2.8874900341033936, | |
| "learning_rate": 1.4246424642464248e-05, | |
| "loss": 1.7986, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 7.334066740007334, | |
| "grad_norm": 2.211998701095581, | |
| "learning_rate": 1.3329666299963331e-05, | |
| "loss": 1.7963, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 7.517418408507518, | |
| "grad_norm": 2.0423145294189453, | |
| "learning_rate": 1.2412907957462413e-05, | |
| "loss": 1.7784, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 7.700770077007701, | |
| "grad_norm": 2.0297274589538574, | |
| "learning_rate": 1.1496149614961496e-05, | |
| "loss": 1.7987, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 7.884121745507884, | |
| "grad_norm": 2.6104135513305664, | |
| "learning_rate": 1.057939127246058e-05, | |
| "loss": 1.7847, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 8.067473414008067, | |
| "grad_norm": 2.4602534770965576, | |
| "learning_rate": 9.662632929959662e-06, | |
| "loss": 1.7903, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 8.250825082508252, | |
| "grad_norm": 2.1262950897216797, | |
| "learning_rate": 8.745874587458746e-06, | |
| "loss": 1.795, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 8.434176751008435, | |
| "grad_norm": 2.538703680038452, | |
| "learning_rate": 7.829116244957828e-06, | |
| "loss": 1.7708, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 8.617528419508618, | |
| "grad_norm": 2.607891321182251, | |
| "learning_rate": 6.912357902456913e-06, | |
| "loss": 1.7824, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 8.800880088008801, | |
| "grad_norm": 2.0636353492736816, | |
| "learning_rate": 5.995599559955996e-06, | |
| "loss": 1.7651, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 8.984231756508985, | |
| "grad_norm": 2.1311886310577393, | |
| "learning_rate": 5.078841217455079e-06, | |
| "loss": 1.7825, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 9.167583425009168, | |
| "grad_norm": 2.185648202896118, | |
| "learning_rate": 4.162082874954162e-06, | |
| "loss": 1.7744, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 9.350935093509351, | |
| "grad_norm": 2.149644374847412, | |
| "learning_rate": 3.2453245324532458e-06, | |
| "loss": 1.781, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 9.534286762009534, | |
| "grad_norm": 2.1185684204101562, | |
| "learning_rate": 2.3285661899523286e-06, | |
| "loss": 1.7712, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 9.717638430509718, | |
| "grad_norm": 2.186683416366577, | |
| "learning_rate": 1.411807847451412e-06, | |
| "loss": 1.7739, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 9.900990099009901, | |
| "grad_norm": 2.319247007369995, | |
| "learning_rate": 4.950495049504951e-07, | |
| "loss": 1.7713, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 27270, | |
| "total_flos": 2.615057185279181e+16, | |
| "train_loss": 1.8617943959923335, | |
| "train_runtime": 1938.923, | |
| "train_samples_per_second": 112.49, | |
| "train_steps_per_second": 14.065 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 27270, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.615057185279181e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |